© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17356
    Prev
    Next
    INDEX
    Explanations

    directions (up, down, out, on)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artin
    -0.12
     Stanton
    -0.11
    aji
    -0.10
     freund
    -0.10
    erb
    -0.10
    _main
    -0.10
    /Main
    -0.09
     Sac
    -0.09
    .native
    -0.09
    edia
    -0.09
    POSITIVE LOGITS
     Inf
    0.09
    inka
    0.08
     bod
    0.08
     Esper
    0.08
    akin
    0.08
     peri
    0.08
    agn
    0.08
     Sans
    0.08
    Sans
    0.08
    éri
    0.08
    Activations Density 0.100%

    No Known Activations